You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by mi...@apache.org on 2011/10/26 16:40:49 UTC

svn commit: r1189246 - in /tika/trunk: CHANGES.txt tika-core/src/main/resources/org/apache/tika/language/lt.ngp tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java

Author: mikemccand
Date: Wed Oct 26 14:40:49 2011
New Revision: 1189246

URL: http://svn.apache.org/viewvc?rev=1189246&view=rev
Log:
TIKA-582: remove extra quotes from Lithuanian 3gram tables

Modified:
    tika/trunk/CHANGES.txt
    tika/trunk/tika-core/src/main/resources/org/apache/tika/language/lt.ngp
    tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java

Modified: tika/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1189246&r1=1189245&r2=1189246&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Wed Oct 26 14:40:49 2011
@@ -22,6 +22,8 @@ Release 0.11 - Current Development
  * TIKA-724: Added option to PDFParser to enable (the default) or
    disable auto-space insertion.
 
+ * TIKA-582: Lithuanian was never detected by LanguageIdentifier.
+
 Release 0.10 - 09/25/2011
 
 The most notable changes in Tika 0.10 over previous releases are:

Modified: tika/trunk/tika-core/src/main/resources/org/apache/tika/language/lt.ngp
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/language/lt.ngp?rev=1189246&r1=1189245&r2=1189246&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/language/lt.ngp (original)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/language/lt.ngp Wed Oct 26 14:40:49 2011
@@ -12,1198 +12,1198 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"ini" 159130
-"s_p" 136654
-"ijo" 122792
-"usi" 109788
-"jos" 107645
-"ien" 102237
-"iau" 101203
-"tin" 98655
-"ali" 97119
-"aus" 96445
-"s_s" 90636
-"o_p" 82919
-"pas" 76537
-"iet" 75896
-"uvo" 73539
-"ink" 72204
-"kai" 70264
-"met" 69573
-"oje" 69524
-"s_i" 69391
-"sta" 69212
-"s_a" 68807
-"etu" 68576
-"lie" 67524
-"tai" 67366
-"s_k" 67201
-"iai" 65565
-"pri" 64365
-"cij" 63754
-"pra" 62815
-"ent" 62543
-"tas" 61206
-"uri" 60404
-"die" 60339
-"s_v" 59941
-"s_t" 59421
-"ant" 59244
-"kur" 58824
-"ist" 58773
-"ais" 58720
-"par" 57557
-"tar" 56888
-"i_p" 56639
-"min" 55905
-"mas" 55042
-"lai" 53592
-"adi" 53477
-"nin" 53428
-"imo" 53282
-"eri" 52816
-"gal" 52650
-"rin" 52324
-"ius" 51954
-"vie" 51668
-"ina" 51595
-"tuv" 51364
-"s_d" 51340
-"inė" 50967
-"s_n" 50915
-"o_s" 50529
-"per" 50345
-"asi" 50040
-"čia" 49622
-"sti" 49324
-"ria" 48966
-"s_b" 48614
-"tik" 48489
-"ų_p" 47566
-"tei" 47284
-"s_m" 46994
-"pro" 46728
-"ija" 46622
-"int" 46240
-"lin" 46223
-"oli" 45286
-"aug" 45194
-"nės" 45165
-"iki" 45097
-"val" 44965
-"kad" 44762
-"rei" 44727
-"eik" 44595
-"ran" 43262
-"ios" 42986
-"art" 42983
-"iam" 42904
-"ama" 42389
-"dar" 41920
-"tra" 41800
-"ari" 41088
-"kar" 40704
-"buv" 40452
-"išk" 40340
-"i_s" 39698
-"nių" 39538
-"toj" 39340
-"o_k" 39240
-"uot" 39079
-"avo" 38925
-"sto" 38437
-"aik" 38434
-"sak" 38392
-"pat" 38170
-"oja" 38106
-"nti" 38046
-"and" 37960
-"nuo" 37925
-"o_a" 37528
-"vai" 37109
-"s_r" 37027
-"rie" 36575
-"ima" 36250
-"dži" 36150
-"ino" 35879
-"kom" 35652
-"enį" 35646
-"ies" 35440
-"aip" 35412
-"o_t" 35270
-"uos" 35175
-"vos" 35022
-"eli" 35016
-"sav" 34879
-"ame" 34802
-"nas" 34747
-"men" 34734
-"est" 34700
-"s_g" 34575
-"kas" 34537
-"end" 34503
-"ų_s" 34397
-"ras" 34268
-"nis" 34174
-"kal" 34092
-"ori" 34018
-"pre" 33908
-"avi" 33907
-"rti" 33845
-"lio" 33617
-"nes" 33416
-"ėjo" 33094
-"ren" 33046
-"o_v" 33041
-"o_m" 33007
-"tur" 32939
-"s_l" 32885
-"ika" 32882
-"ter" 32591
-"aut" 32530
-"nio" 32467
-"mon" 32251
-"sia" 31903
-"ris" 31726
-"lia" 31598
-"eis" 31331
-"ų_k" 31214
-"sio" 31193
-"var" 30935
-"pir" 30876
-"nia" 30796
-"ose" 30724
-"aci" 30646
-"etų" 30333
-"eni" 30096
-"eig" 29982
-"iti" 29963
-"rad" 29834
-"ats" 29741
-"ing" 29643
-"nka" 29366
-"kon" 29259
-"mis" 29240
-"aud" 29189
-"eči" 29187
-"omi" 29121
-"tos" 28908
-"o_i" 28902
-"a_p" 28666
-"nta" 28206
-"e_p" 28094
-"irt" 28062
-"iko" 28035
-"i_i" 28032
-"kla" 28004
-"are" 27968
-"din" 27854
-"ili" 27784
-"i_n" 27745
-"tis" 27740
-"lau" 27597
-"tat" 27590
-"kin" 27293
-"nau" 27284
-"asa" 27223
-"o_d" 27142
-"o_n" 27018
-"kel" 26795
-"vis" 26752
-"ati" 26751
-"irm" 26533
-"jam" 26466
-"auj" 26466
-"ų_m" 26457
-"oma" 26174
-"o_r" 26138
-"s_į" 26036
-"gia" 26032
-"oni" 25744
-"vir" 25725
-"tor" 25626
-"riu" 25603
-"nči" 25544
-"sus" 25479
-"i_k" 25472
-"oti" 25423
-"vyk" 25288
-"iek" 25282
-"gin" 25205
-"ala" 25159
-"ntr" 25023
-"i_a" 25011
-"sij" 24954
-"i_t" 24940
-"ici" 24880
-"kos" 24822
-"enk" 24585
-"čių" 24491
-"sau" 24328
-"eti" 24311
-"raš" 24191
-"joj" 24153
-"ane" 24141
-"žia" 24121
-"sie" 24115
-"ams" 24113
-"ben" 24113
-"auk" 24112
-"ita" 24110
-"isi" 24026
-"dau" 24009
-"pie" 23921
-"str" 23827
-"i_b" 23715
-"lan" 23667
-"imu" 23615
-"ų_a" 23535
-"tvi" 23473
-"ide" 23466
-"ndr" 23419
-"ato" 23399
-"dėl" 23394
-"api" 23356
-"rij" 23263
-"nto" 23215
-"yra" 23185
-"ova" 23113
-"čio" 23058
-"ste" 22985
-"man" 22817
-"lit" 22796
-"iuo" 22568
-"ani" 22553
-"aty" 22469
-"den" 22448
-"ket" 22424
-"kia" 22396
-"ojo" 22359
-"į_p" 22318
-"anč" 22302
-"nim" 22280
-"Å¡al" 22185
-"ank" 22164
-"ena" 22156
-"ų_i" 22156
-"nus" 22144
-"jus" 22125
-"ona" 22054
-"yti" 22020
-"ami" 22001
-"arb" 21994
-"sis" 21922
-"rio" 21744
-"mok" 21682
-"did" 21672
-"ybė" 21613
-"ver" 21543
-"ska" 21465
-"rau" 21450
-"ekt" 21440
-"e_s" 21419
-"imą" 21261
-"tus" 21109
-"vil" 21091
-"ven" 21066
-"žin" 21062
-"ara" 21052
-"rus" 21051
-"nij" 21022
-"nam" 21022
-"kti" 20974
-"ado" 20929
-"eta" 20911
-"tuo" 20890
-"rta" 20873
-"s_Å¡" 20708
-"ion" 20705
-"lių" 20689
-"vei" 20533
-"lis" 20474
-"rių" 20379
-"ast" 20374
-"nai" 20365
-"čiu" 20363
-"tie" 20293
-"mos" 20283
-"bus" 20273
-"s_j" 20268
-"r_p" 20206
-"eng" 20174
-"i_v" 20169
-"o_b" 20158
-"gos" 20137
-"ele" 20087
-"ieš" 20063
-"ą_p" 20059
-"jau" 20027
-"uti" 20025
-"era" 19968
-"lik" 19958
-"tij" 19908
-"ung" 19882
-"vad" 19855
-"eto" 19718
-"ų_t" 19633
-"liu" 19624
-"i_d" 19601
-"oki" 19582
-"ngt" 19529
-"mai" 19489
-"neš" 19415
-"yri" 19405
-"rit" 19243
-"yje" 19202
-"kim" 19120
-"osi" 19078
-"nki" 19069
-"pol" 19036
-"rim" 19028
-"alt" 19022
-"als" 19011
-"eno" 18995
-"rma" 18938
-"dal" 18885
-"tad" 18884
-"ndi" 18860
-"ų_v" 18848
-"bos" 18781
-"o_l" 18727
-"niu" 18697
-"ači" 18695
-"oto" 18673
-"net" 18634
-"jai" 18624
-"ait" 18614
-"sit" 18587
-"kus" 18537
-"vim" 18536
-"ald" 18495
-"rez" 18473
-"a_s" 18465
-"ata" 18455
-"amo" 18413
-"ava" 18311
-"aly" 18250
-"ana" 18208
-"tre" 18204
-"uli" 18184
-"rov" 18140
-"atv" 18079
-"uoj" 18032
-"ano" 17974
-"nos" 17947
-"imi" 17884
-"ada" 17864
-"tel" 17860
-"o_g" 17819
-"uro" 17810
-"ard" 17719
-"pal" 17667
-"tan" 17658
-"itų" 17649
-"gyv" 17619
-"ome" 17569
-"pag" 17541
-"dam" 17540
-"vyr" 17522
-"ask" 17461
-"tro" 17412
-"kst" 17335
-"akė" 17298
-"bei" 17263
-"spa" 17211
-"kra" 17183
-"ros" 17135
-"rod" 17133
-"uto" 17098
-"ias" 17082
-"maž" 17076
-"omo" 17037
-"vas" 17028
-"iči" 17022
-"nal" 17009
-"esi" 16800
-"dos" 16758
-"duo" 16757
-"jas" 16752
-"lei" 16688
-"ate" 16619
-"roc" 16602
-"iem" 16589
-"tam" 16562
-"ybo" 16532
-"u_p" 16409
-"iją" 16383
-"ers" 16264
-"e_t" 16234
-"ono" 16134
-"ų_b" 16110
-"lst" 16086
-"ų_n" 16065
-"kta" 16061
-"jim" 16039
-"tom" 16004
-"mus" 15977
-"kci" 15963
-"ų_d" 15960
-"sty" 15882
-"ų_g" 15857
-"pos" 15821
-"rek" 15812
-"aid" 15739
-"bal" 15684
-"dra" 15594
-"i_į" 15593
-"mie" 15582
-"ary" 15559
-"a_i" 15555
-"rai" 15550
-"rat" 15545
-"ijų" 15534
-"kie" 15508
-"ian" 15508
-"ioj" 15482
-"dro" 15466
-"bės" 15465
-"iln" 15425
-"nkt" 15412
-"ral" 15410
-"ert" 15393
-"tyb" 15390
-"o_į" 15324
-"ėje" 15293
-"žmo" 15281
-"igi" 15265
-"aba" 15257
-"lni" 15239
-"bai" 15239
-"ą_s" 15144
-"ė_p" 15124
-"ų_r" 15008
-"alė" 14978
-"uom" 14974
-"der" 14955
-"ovė" 14936
-"aka" 14870
-"ugi" 14862
-"dov" 14824
-"ruo" 14818
-"aro" 14818
-"s_e" 14673
-"ikt" 14650
-"arp" 14646
-"ain" 14644
-"s_ž" 14641
-"pen" 14640
-"Å¡ki" 14593
-"san" 14569
-"cia" 14546
-"sir" 14505
-"lti" 14465
-"dai" 14456
-"a_n" 14448
-"kit" 14440
-"aži" 14437
-"gra" 14319
-"ime" 14286
-"kam" 14253
-"tri" 14251
-"e_v" 14250
-"eši" 14202
-"imt" 14193
-"dim" 14179
-"r_k" 14168
-"ą_i" 14135
-"spr" 14131
-"ito" 14124
-"pan" 14115
-"aul" 14114
-"yve" 14095
-"pav" 14071
-"ner" 14051
-"eur" 13954
-"tau" 13937
-"žio" 13930
-"ų_l" 13916
-"rto" 13877
-"ust" 13854
-"pak" 13852
-"pad" 13829
-"eki" 13779
-"Å¡ia" 13774
-"aig" 13762
-"kau" 13753
-"nep" 13732
-"kri" 13644
-"ski" 13633
-"sių" 13605
-"ost" 13600
-"lim" 13597
-"ėju" 13587
-"aun" 13583
-"ban" 13544
-"i_g" 13517
-"tov" 13513
-"nko" 13466
-"ira" 13449
-"ėja" 13447
-"len" 13440
-"yta" 13425
-"nar" 13424
-"nie" 13401
-"ėti" 13316
-"dėj" 13293
-"nor" 13275
-"siu" 13253
-"e_b" 13248
-"a_a" 13246
-"lic" 13246
-"tim" 13243
-"jav" 13213
-"ale" 13208
-"uja" 13190
-"sin" 13189
-"ram" 13151
-"kre" 13121
-"ezi" 13114
-"uma" 13099
-"eks" 13075
-"tač" 13002
-"a_t" 12982
-"voj" 12981
-"ial" 12980
-"urė" 12968
-"uol" 12911
-"ieč" 12891
-"ida" 12884
-"kan" 12866
-"i_l" 12853
-"jog" 12839
-"das" 12838
-"bil" 12835
-"į_s" 12830
-"kto" 12829
-"nei" 12813
-"rik" 12801
-"būt" 12789
-"por" 12770
-"i_m" 12759
-"aim" 12632
-"ang" 12611
-"rga" 12591
-"jis" 12591
-"Å¡io" 12576
-"ngi" 12558
-"imų" 12541
-"ota" 12524
-"eim" 12513
-"zid" 12504
-"s_u" 12449
-"dir" 12442
-"e_i" 12415
-"Å¡im" 12412
-"iva" 12405
-"ine" 12393
-"ikė" 12320
-"i_r" 12308
-"r_s" 12298
-"ort" 12293
-"eko" 12282
-"jun" 12256
-"ovo" 12171
-"onė" 12170
-"bin" 12164
-"lės" 12157
-"jan" 12151
-"cen" 12147
-"epa" 12142
-"gim" 12127
-"u_s" 12107
-"ind" 12092
-"ite" 12003
-"e_a" 12002
-"a_k" 11998
-"pla" 11983
-"mer" 11978
-"uta" 11950
-"nga" 11945
-"idž" 11939
-"tru" 11932
-"u_k" 11907
-"pau" 11865
-"e_n" 11864
-"ngo" 11838
-"i_j" 11823
-"e_k" 11812
-"eid" 11810
-"for" 11809
-"akc" 11799
-"kir" 11796
-"nat" 11777
-"nda" 11692
-"reč" 11641
-"aps" 11640
-"p_p" 11639
-"gai" 11634
-"paž" 11629
-"sut" 11625
-"emo" 11619
-"ryt" 11614
-"rna" 11610
-"one" 11601
-"opo" 11589
-"tyn" 11551
-"ešė" 11544
-"ern" 11540
-"ene" 11540
-"nan" 11536
-"akt" 11533
-"kio" 11529
-"mat" 11527
-"mad" 11519
-"gru" 11477
-"isa" 11403
-"kov" 11353
-"gan" 11309
-"dav" 11291
-"udo" 11290
-"tūr" 11243
-"oji" 11237
-"tst" 11236
-"tok" 11229
-"a_d" 11220
-"adė" 11220
-"nte" 11201
-"ikr" 11196
-"cin" 11174
-"iri" 11157
-"erg" 11122
-"aga" 11120
-"las" 11109
-"etv" 11089
-"Å¡in" 11066
-"ikl" 11053
-"obi" 11044
-"gti" 11041
-"tal" 11032
-"spe" 11027
-"u_n" 11020
-"ųjų" 11019
-"rop" 10969
-"vin" 10960
-"kol" 10877
-"r_t" 10860
-"nom" 10852
-"uda" 10836
-"eną" 10829
-"ans" 10822
-"ger" 10812
-"lta" 10812
-"i_Å¡" 10779
-"nci" 10778
-"mln" 10764
-"olo" 10754
-"lyg" 10730
-"lij" 10719
-"gen" 10718
-"Å«ks" 10695
-"jon" 10669
-"vės" 10657
-"r_v" 10651
-"dyt" 10638
-"ybi" 10624
-"itu" 10607
-"evi" 10584
-"sek" 10570
-"s_f" 10547
-"idė" 10534
-"orm" 10517
-"e_d" 10516
-"stu" 10514
-"į_k" 10512
-"įst" 10484
-"tsi" 10461
-"inę" 10412
-"ako" 10388
-"umo" 10365
-"yva" 10357
-"alb" 10341
-"tūk" 10323
-"ė_s" 10298
-"tės" 10268
-"nėj" 10233
-"a_b" 10218
-"o_Å¡" 10201
-"igo" 10143
-"Å¡ka" 10112
-"a_v" 10108
-"mob" 10106
-"sim" 10086
-"rog" 10077
-"rtu" 10048
-"ndo" 10024
-"r_n" 10015
-"Å«na" 9995
-"ero" 9990
-"uni" 9954
-"tyt" 9935
-"mpi" 9904
-"ere" 9871
-"gri" 9864
-"edi" 9816
-"ark" 9766
-"ins" 9754
-"kių" 9737
-"eiš" 9737
-"alo" 9715
-"idi" 9710
-"gas" 9700
-"ten" 9695
-"ėji" 9687
-"vid" 9668
-"sei" 9648
-"o_j" 9646
-"ą_k" 9642
-"bar" 9565
-"usk" 9557
-"ber" 9487
-"pin" 9481
-"klu" 9472
-"mėn" 9467
-"gam" 9454
-"dij" 9439
-"inu" 9430
-"įsi" 9410
-"iej" 9390
-"rem" 9381
-"rmi" 9348
-"dvi" 9348
-"nku" 9326
-"res" 9307
-"igū" 9273
-"sik" 9270
-"esn" 9248
-"ugo" 9235
-"dan" 9230
-"mar" 9202
-"vak" 9193
-"uga" 9182
-"r_a" 9181
-"gūn" 9179
-"vus" 9171
-"atl" 9171
-"elb" 9153
-"rda" 9147
-"zij" 9123
-"užs" 9112
-"į_v" 9094
-"rup" 9082
-"roj" 9043
-"ems" 9041
-"kis" 9016
-"Å¡ta" 8987
-"muo" 8960
-"udi" 8915
-"lat" 8903
-"lėj" 8902
-"ute" 8892
-"ote" 8883
-"ą_a" 8855
-"rak" 8834
-"ą_v" 8823
-"ėne" 8784
-"iks" 8762
-"nyb" 8762
-"pil" 8709
-"r_d" 8697
-"ske" 8691
-"arn" 8676
-"ult" 8649
-"tol" 8648
-"ymo" 8646
-"žai" 8632
-"nkl" 8601
-"iui" 8557
-"fin" 8546
-"u_t" 8539
-"u_a" 8508
-"ido" 8505
-"kli" 8473
-"sid" 8470
-"ntu" 8469
-"kyt" 8465
-"sni" 8462
-"kil" 8451
-"ldy" 8426
-"rės" 8421
-"gar" 8403
-"ė_v" 8374
-"lam" 8356
-"ėli" 8344
-"gau" 8327
-"rac" 8301
-"rėj" 8293
-"sme" 8293
-"sen" 8274
-"mui" 8272
-"sas" 8272
-"iza" 8269
-"ojų" 8250
-"les" 8233
-"a_l" 8227
-"aiš" 8217
-"ryb" 8199
-"esa" 8186
-"Å«ro" 8184
-"ega" 8181
-"kat" 8166
-"egi" 8165
-"ė_a" 8149
-"sla" 8142
-"mot" 8130
-"usy" 8121
-"eit" 8115
-"inį" 8108
-"air" 8102
-"tit" 8093
-"ole" 8084
-"lyv" 8084
-"jie" 8068
-"lek" 8047
-"suo" 8046
-"spo" 8030
-"bas" 8030
-"ukt" 8023
-"ula" 8016
-"Å«ti" 8008
-"del" 8003
-"enc" 7995
-"kšt" 7982
-"arė" 7972
-"mės" 7972
-"emp" 7971
-"los" 7970
-"dom" 7933
-"bia" 7927
-"van" 7922
-"enė" 7913
-"Å¡ko" 7910
-"run" 7906
-"iku" 7895
-"u_b" 7892
-"yni" 7887
-"sku" 7881
-"žsi" 7880
-"šių" 7877
-"iav" 7872
-"mes" 7847
-"lyj" 7841
-"pus" 7826
-"uva" 7823
-"ton" 7813
-"rny" 7813
-"sve" 7811
-"ašt" 7803
-"siū" 7797
-"ivi" 7797
-"tek" 7796
-"myb" 7781
-"alų" 7767
-"omp" 7745
-"į_a" 7742
-"emi" 7739
-"med" 7732
-"e_r" 7726
-"ė_k" 7715
-"škė" 7710
-"ont" 7709
-"sul" 7683
-"lėt" 7675
-"ą_d" 7675
-"ėse" 7655
-"suk" 7651
-"tym" 7643
-"eda" 7620
-"ire" 7614
-"įvy" 7610
-"dėt" 7605
-"tap" 7602
-"vau" 7601
-"sči" 7598
-"oms" 7597
-"iūl" 7587
-"u_i" 7575
-"yto" 7565
-"žiu" 7563
-"išs" 7562
-"org" 7543
-"šči" 7533
-"mėj" 7529
-"ars" 7528
-"Å¡iu" 7516
-"pel" 7513
-"gre" 7512
-"aur" 7494
-"ešt" 7478
-"izi" 7458
-"agr" 7457
-"idu" 7453
-"sva" 7443
-"ą_b" 7431
-"tyv" 7431
-"a_g" 7422
-"irb" 7416
-"e_g" 7411
-"sur" 7410
-"rba" 7401
-"gum" 7396
-"ė_n" 7383
-"sos" 7381
-"ų_į" 7378
-"e_l" 7378
-"urn" 7372
-"vič" 7370
-"nkų" 7367
-"ksl" 7365
-"ler" 7364
-"ėtų" 7359
-"u_v" 7355
-"syb" 7347
-"aki" 7340
-"kij" 7339
-"kėj" 7334
-"oks" 7327
-"lab" 7291
-"rys" 7280
-"gij" 7272
-"ašk" 7259
-"pio" 7258
-"ism" 7250
-"oka" 7236
-"ves" 7209
-"o_ž" 7205
-"igė" 7199
-"bri" 7191
-"iad" 7190
-"o_e" 7180
-"juo" 7175
-"r_m" 7171
-"ipa" 7170
-"stų" 7157
-"ons" 7153
-"klo" 7148
-"ovi" 7126
-"nut" 7117
-"puo" 7111
-"šeš" 7107
-"o_u" 7105
-"etr" 7100
-"vok" 7097
-"oju" 7077
-"via" 7064
-"imė" 7056
-"e_m" 7052
-"tyr" 7050
-"ete" 7022
-"sum" 7021
-"ogi" 7011
-"log" 6992
-"sud" 6968
-"r_j" 6961
-"amu" 6953
-"bet" 6952
-"rbi" 6951
-"pta" 6947
-"urt" 6937
-"ure" 6934
-"žei" 6930
-"tys" 6930
-"gus" 6903
-"Å¡ve" 6891
-"ens" 6889
-"ąją" 6882
-"žem" 6863
-"įmo" 6858
-"sar" 6852
-"abi" 6849
-"gty" 6849
-"inf" 6844
-"eži" 6830
-"taš" 6818
-"Å¡ti" 6811
-"aru" 6808
-"s_o" 6785
-"rtą" 6773
-"ą_n" 6766
-"uvi" 6754
-"ė_i" 6750
-"į_i" 6749
-"mil" 6747
-"odė" 6745
-"rėt" 6727
-"yba" 6726
-"aėj" 6725
-"raė" 6716
-"reg" 6715
-"dym" 6713
-"eln" 6712
-"ujo" 6681
-"s_y" 6680
-"a_m" 6679
-"vių" 6670
-"age" 6668
-"rep" 6661
-"rdu" 6660
-"ilo" 6634
-"uod" 6619
-"viz" 6616
-"sko" 6610
-"eka" 6603
-"ėmi" 6584
-"koj" 6572
-"yks" 6556
-"neb" 6554
-"ake" 6552
-"į_l" 6545
-"oci" 6520
-"dyb" 6500
-"ų_š" 6478
-"nst" 6474
-"t_p" 6463
-"bol" 6459
-"bra" 6457
-"lub" 6451
-"oro" 6450
-"čem" 6442
-"aja" 6440
-"doj" 6440
-"lyd" 6430
-"rol" 6428
-"pab" 6428
-"lig" 6426
-"bėj" 6382
-"a_į" 6372
-"amų" 6369
-"amb" 6363
-"į_t" 6362
-"ykl" 6362
-"r_l" 6362
-"asm" 6334
-"yvi" 6333
-"į_n" 6333
-"ktu" 6322
-"iga" 6321
-"anc" 6317
-"niz" 6308
-"nks" 6306
-"s_c" 6296
-"fer" 6289
-"pti" 6277
-"yko" 6276
-"ą_t" 6271
-"ser" 6268
-"nde" 6267
-"ė_d" 6263
-"ola" 6261
-"kor" 6250
-"ė_t" 6220
-"sąj" 6208
-"ret" 6200
-"lbė" 6194
-"tli" 6188
-"oku" 6185
-"ąju" 6179
-"ntų" 6173
-"u_m" 6128
-"ema" 6118
-"sli" 6111
-"ipė" 6106
-"ugu" 6100
-"mac" 6082
-"sig" 6070
-"uki" 6049
-"nfo" 6033
-"atr" 6028
-"iso" 6025
-"pap" 6023
-"Å¡au" 6010
-"u_d" 5991
-"r_b" 5990
-"iju" 5987
-"ogr" 5984
-"rob" 5981
-"num" 5979
-"paj" 5978
-"iru" 5977
-"raj" 5965
-"u_j" 5961
-"ajo" 5956
-"ora" 5950
-"tes" 5948
-"oda" 5935
-"išv" 5935
-"upė" 5932
-"vėl" 5928
-"soc" 5926
-"amą" 5923
-"lgi" 5917
-"o_f" 5917
-"a_r" 5913
-"uno" 5913
-"ael" 5903
-"rae" 5898
-"kiu" 5895
-"moj" 5894
-"jek" 5873
-"sil" 5873
-"ėsi" 5863
-"isu" 5862
-"ų_e" 5862
-"i_ž" 5858
-"rst" 5853
-"uje" 5851
-"įta" 5848
-"goj" 5845
-"ruk" 5842
-"mti" 5839
-"imy" 5787
-"ukš" 5781
-"sky" 5777
-"neg" 5770
-"noj" 5746
-"apt" 5736
-"dab" 5732
-"vij" 5718
-"enų" 5714
-"mir" 5710
-"iuj" 5710
-"uzi" 5708
-"nty" 5706
-"kyb" 5693
-"isk" 5683
-"gel" 5680
-"lon" 5678
-"mpa" 5668
-"e_į" 5664
-"ė_j" 5659
-"mia" 5653
-"l_k" 5650
-"apo" 5643
-"riv" 5634
-"ašy" 5614
-"rbu" 5611
-"kty" 5602
-"ond" 5597
-"enu" 5595
-"ope" 5587
-"ila" 5585
-"kei" 5578
-"tėj" 5562
-"lav" 5552
-"rbo" 5547
-"Å¡ie" 5530
-"nkė" 5517
-"iky" 5504
-"tet" 5500
+ini 159130
+s_p 136654
+ijo 122792
+usi 109788
+jos 107645
+ien 102237
+iau 101203
+tin 98655
+ali 97119
+aus 96445
+s_s 90636
+o_p 82919
+pas 76537
+iet 75896
+uvo 73539
+ink 72204
+kai 70264
+met 69573
+oje 69524
+s_i 69391
+sta 69212
+s_a 68807
+etu 68576
+lie 67524
+tai 67366
+s_k 67201
+iai 65565
+pri 64365
+cij 63754
+pra 62815
+ent 62543
+tas 61206
+uri 60404
+die 60339
+s_v 59941
+s_t 59421
+ant 59244
+kur 58824
+ist 58773
+ais 58720
+par 57557
+tar 56888
+i_p 56639
+min 55905
+mas 55042
+lai 53592
+adi 53477
+nin 53428
+imo 53282
+eri 52816
+gal 52650
+rin 52324
+ius 51954
+vie 51668
+ina 51595
+tuv 51364
+s_d 51340
+inė 50967
+s_n 50915
+o_s 50529
+per 50345
+asi 50040
+čia 49622
+sti 49324
+ria 48966
+s_b 48614
+tik 48489
+ų_p 47566
+tei 47284
+s_m 46994
+pro 46728
+ija 46622
+int 46240
+lin 46223
+oli 45286
+aug 45194
+nės 45165
+iki 45097
+val 44965
+kad 44762
+rei 44727
+eik 44595
+ran 43262
+ios 42986
+art 42983
+iam 42904
+ama 42389
+dar 41920
+tra 41800
+ari 41088
+kar 40704
+buv 40452
+išk 40340
+i_s 39698
+nių 39538
+toj 39340
+o_k 39240
+uot 39079
+avo 38925
+sto 38437
+aik 38434
+sak 38392
+pat 38170
+oja 38106
+nti 38046
+and 37960
+nuo 37925
+o_a 37528
+vai 37109
+s_r 37027
+rie 36575
+ima 36250
+dži 36150
+ino 35879
+kom 35652
+enį 35646
+ies 35440
+aip 35412
+o_t 35270
+uos 35175
+vos 35022
+eli 35016
+sav 34879
+ame 34802
+nas 34747
+men 34734
+est 34700
+s_g 34575
+kas 34537
+end 34503
+ų_s 34397
+ras 34268
+nis 34174
+kal 34092
+ori 34018
+pre 33908
+avi 33907
+rti 33845
+lio 33617
+nes 33416
+ėjo 33094
+ren 33046
+o_v 33041
+o_m 33007
+tur 32939
+s_l 32885
+ika 32882
+ter 32591
+aut 32530
+nio 32467
+mon 32251
+sia 31903
+ris 31726
+lia 31598
+eis 31331
+ų_k 31214
+sio 31193
+var 30935
+pir 30876
+nia 30796
+ose 30724
+aci 30646
+etų 30333
+eni 30096
+eig 29982
+iti 29963
+rad 29834
+ats 29741
+ing 29643
+nka 29366
+kon 29259
+mis 29240
+aud 29189
+eči 29187
+omi 29121
+tos 28908
+o_i 28902
+a_p 28666
+nta 28206
+e_p 28094
+irt 28062
+iko 28035
+i_i 28032
+kla 28004
+are 27968
+din 27854
+ili 27784
+i_n 27745
+tis 27740
+lau 27597
+tat 27590
+kin 27293
+nau 27284
+asa 27223
+o_d 27142
+o_n 27018
+kel 26795
+vis 26752
+ati 26751
+irm 26533
+jam 26466
+auj 26466
+ų_m 26457
+oma 26174
+o_r 26138
+s_į 26036
+gia 26032
+oni 25744
+vir 25725
+tor 25626
+riu 25603
+nči 25544
+sus 25479
+i_k 25472
+oti 25423
+vyk 25288
+iek 25282
+gin 25205
+ala 25159
+ntr 25023
+i_a 25011
+sij 24954
+i_t 24940
+ici 24880
+kos 24822
+enk 24585
+čių 24491
+sau 24328
+eti 24311
+raš 24191
+joj 24153
+ane 24141
+žia 24121
+sie 24115
+ams 24113
+ben 24113
+auk 24112
+ita 24110
+isi 24026
+dau 24009
+pie 23921
+str 23827
+i_b 23715
+lan 23667
+imu 23615
+ų_a 23535
+tvi 23473
+ide 23466
+ndr 23419
+ato 23399
+dėl 23394
+api 23356
+rij 23263
+nto 23215
+yra 23185
+ova 23113
+čio 23058
+ste 22985
+man 22817
+lit 22796
+iuo 22568
+ani 22553
+aty 22469
+den 22448
+ket 22424
+kia 22396
+ojo 22359
+į_p 22318
+anč 22302
+nim 22280
+Å¡al 22185
+ank 22164
+ena 22156
+ų_i 22156
+nus 22144
+jus 22125
+ona 22054
+yti 22020
+ami 22001
+arb 21994
+sis 21922
+rio 21744
+mok 21682
+did 21672
+ybė 21613
+ver 21543
+ska 21465
+rau 21450
+ekt 21440
+e_s 21419
+imą 21261
+tus 21109
+vil 21091
+ven 21066
+žin 21062
+ara 21052
+rus 21051
+nij 21022
+nam 21022
+kti 20974
+ado 20929
+eta 20911
+tuo 20890
+rta 20873
+s_Å¡ 20708
+ion 20705
+lių 20689
+vei 20533
+lis 20474
+rių 20379
+ast 20374
+nai 20365
+čiu 20363
+tie 20293
+mos 20283
+bus 20273
+s_j 20268
+r_p 20206
+eng 20174
+i_v 20169
+o_b 20158
+gos 20137
+ele 20087
+ieš 20063
+ą_p 20059
+jau 20027
+uti 20025
+era 19968
+lik 19958
+tij 19908
+ung 19882
+vad 19855
+eto 19718
+ų_t 19633
+liu 19624
+i_d 19601
+oki 19582
+ngt 19529
+mai 19489
+neš 19415
+yri 19405
+rit 19243
+yje 19202
+kim 19120
+osi 19078
+nki 19069
+pol 19036
+rim 19028
+alt 19022
+als 19011
+eno 18995
+rma 18938
+dal 18885
+tad 18884
+ndi 18860
+ų_v 18848
+bos 18781
+o_l 18727
+niu 18697
+ači 18695
+oto 18673
+net 18634
+jai 18624
+ait 18614
+sit 18587
+kus 18537
+vim 18536
+ald 18495
+rez 18473
+a_s 18465
+ata 18455
+amo 18413
+ava 18311
+aly 18250
+ana 18208
+tre 18204
+uli 18184
+rov 18140
+atv 18079
+uoj 18032
+ano 17974
+nos 17947
+imi 17884
+ada 17864
+tel 17860
+o_g 17819
+uro 17810
+ard 17719
+pal 17667
+tan 17658
+itų 17649
+gyv 17619
+ome 17569
+pag 17541
+dam 17540
+vyr 17522
+ask 17461
+tro 17412
+kst 17335
+akė 17298
+bei 17263
+spa 17211
+kra 17183
+ros 17135
+rod 17133
+uto 17098
+ias 17082
+maž 17076
+omo 17037
+vas 17028
+iči 17022
+nal 17009
+esi 16800
+dos 16758
+duo 16757
+jas 16752
+lei 16688
+ate 16619
+roc 16602
+iem 16589
+tam 16562
+ybo 16532
+u_p 16409
+iją 16383
+ers 16264
+e_t 16234
+ono 16134
+ų_b 16110
+lst 16086
+ų_n 16065
+kta 16061
+jim 16039
+tom 16004
+mus 15977
+kci 15963
+ų_d 15960
+sty 15882
+ų_g 15857
+pos 15821
+rek 15812
+aid 15739
+bal 15684
+dra 15594
+i_į 15593
+mie 15582
+ary 15559
+a_i 15555
+rai 15550
+rat 15545
+ijų 15534
+kie 15508
+ian 15508
+ioj 15482
+dro 15466
+bės 15465
+iln 15425
+nkt 15412
+ral 15410
+ert 15393
+tyb 15390
+o_į 15324
+ėje 15293
+žmo 15281
+igi 15265
+aba 15257
+lni 15239
+bai 15239
+ą_s 15144
+ė_p 15124
+ų_r 15008
+alė 14978
+uom 14974
+der 14955
+ovė 14936
+aka 14870
+ugi 14862
+dov 14824
+ruo 14818
+aro 14818
+s_e 14673
+ikt 14650
+arp 14646
+ain 14644
+s_ž 14641
+pen 14640
+Å¡ki 14593
+san 14569
+cia 14546
+sir 14505
+lti 14465
+dai 14456
+a_n 14448
+kit 14440
+aži 14437
+gra 14319
+ime 14286
+kam 14253
+tri 14251
+e_v 14250
+eši 14202
+imt 14193
+dim 14179
+r_k 14168
+ą_i 14135
+spr 14131
+ito 14124
+pan 14115
+aul 14114
+yve 14095
+pav 14071
+ner 14051
+eur 13954
+tau 13937
+žio 13930
+ų_l 13916
+rto 13877
+ust 13854
+pak 13852
+pad 13829
+eki 13779
+Å¡ia 13774
+aig 13762
+kau 13753
+nep 13732
+kri 13644
+ski 13633
+sių 13605
+ost 13600
+lim 13597
+ėju 13587
+aun 13583
+ban 13544
+i_g 13517
+tov 13513
+nko 13466
+ira 13449
+ėja 13447
+len 13440
+yta 13425
+nar 13424
+nie 13401
+ėti 13316
+dėj 13293
+nor 13275
+siu 13253
+e_b 13248
+a_a 13246
+lic 13246
+tim 13243
+jav 13213
+ale 13208
+uja 13190
+sin 13189
+ram 13151
+kre 13121
+ezi 13114
+uma 13099
+eks 13075
+tač 13002
+a_t 12982
+voj 12981
+ial 12980
+urė 12968
+uol 12911
+ieč 12891
+ida 12884
+kan 12866
+i_l 12853
+jog 12839
+das 12838
+bil 12835
+į_s 12830
+kto 12829
+nei 12813
+rik 12801
+būt 12789
+por 12770
+i_m 12759
+aim 12632
+ang 12611
+rga 12591
+jis 12591
+Å¡io 12576
+ngi 12558
+imų 12541
+ota 12524
+eim 12513
+zid 12504
+s_u 12449
+dir 12442
+e_i 12415
+Å¡im 12412
+iva 12405
+ine 12393
+ikė 12320
+i_r 12308
+r_s 12298
+ort 12293
+eko 12282
+jun 12256
+ovo 12171
+onė 12170
+bin 12164
+lės 12157
+jan 12151
+cen 12147
+epa 12142
+gim 12127
+u_s 12107
+ind 12092
+ite 12003
+e_a 12002
+a_k 11998
+pla 11983
+mer 11978
+uta 11950
+nga 11945
+idž 11939
+tru 11932
+u_k 11907
+pau 11865
+e_n 11864
+ngo 11838
+i_j 11823
+e_k 11812
+eid 11810
+for 11809
+akc 11799
+kir 11796
+nat 11777
+nda 11692
+reč 11641
+aps 11640
+p_p 11639
+gai 11634
+paž 11629
+sut 11625
+emo 11619
+ryt 11614
+rna 11610
+one 11601
+opo 11589
+tyn 11551
+ešė 11544
+ern 11540
+ene 11540
+nan 11536
+akt 11533
+kio 11529
+mat 11527
+mad 11519
+gru 11477
+isa 11403
+kov 11353
+gan 11309
+dav 11291
+udo 11290
+tūr 11243
+oji 11237
+tst 11236
+tok 11229
+a_d 11220
+adė 11220
+nte 11201
+ikr 11196
+cin 11174
+iri 11157
+erg 11122
+aga 11120
+las 11109
+etv 11089
+Å¡in 11066
+ikl 11053
+obi 11044
+gti 11041
+tal 11032
+spe 11027
+u_n 11020
+ųjų 11019
+rop 10969
+vin 10960
+kol 10877
+r_t 10860
+nom 10852
+uda 10836
+eną 10829
+ans 10822
+ger 10812
+lta 10812
+i_Å¡ 10779
+nci 10778
+mln 10764
+olo 10754
+lyg 10730
+lij 10719
+gen 10718
+Å«ks 10695
+jon 10669
+vės 10657
+r_v 10651
+dyt 10638
+ybi 10624
+itu 10607
+evi 10584
+sek 10570
+s_f 10547
+idė 10534
+orm 10517
+e_d 10516
+stu 10514
+į_k 10512
+įst 10484
+tsi 10461
+inę 10412
+ako 10388
+umo 10365
+yva 10357
+alb 10341
+tūk 10323
+ė_s 10298
+tės 10268
+nėj 10233
+a_b 10218
+o_Å¡ 10201
+igo 10143
+Å¡ka 10112
+a_v 10108
+mob 10106
+sim 10086
+rog 10077
+rtu 10048
+ndo 10024
+r_n 10015
+Å«na 9995
+ero 9990
+uni 9954
+tyt 9935
+mpi 9904
+ere 9871
+gri 9864
+edi 9816
+ark 9766
+ins 9754
+kių 9737
+eiš 9737
+alo 9715
+idi 9710
+gas 9700
+ten 9695
+ėji 9687
+vid 9668
+sei 9648
+o_j 9646
+ą_k 9642
+bar 9565
+usk 9557
+ber 9487
+pin 9481
+klu 9472
+mėn 9467
+gam 9454
+dij 9439
+inu 9430
+įsi 9410
+iej 9390
+rem 9381
+rmi 9348
+dvi 9348
+nku 9326
+res 9307
+igū 9273
+sik 9270
+esn 9248
+ugo 9235
+dan 9230
+mar 9202
+vak 9193
+uga 9182
+r_a 9181
+gūn 9179
+vus 9171
+atl 9171
+elb 9153
+rda 9147
+zij 9123
+užs 9112
+į_v 9094
+rup 9082
+roj 9043
+ems 9041
+kis 9016
+Å¡ta 8987
+muo 8960
+udi 8915
+lat 8903
+lėj 8902
+ute 8892
+ote 8883
+ą_a 8855
+rak 8834
+ą_v 8823
+ėne 8784
+iks 8762
+nyb 8762
+pil 8709
+r_d 8697
+ske 8691
+arn 8676
+ult 8649
+tol 8648
+ymo 8646
+žai 8632
+nkl 8601
+iui 8557
+fin 8546
+u_t 8539
+u_a 8508
+ido 8505
+kli 8473
+sid 8470
+ntu 8469
+kyt 8465
+sni 8462
+kil 8451
+ldy 8426
+rės 8421
+gar 8403
+ė_v 8374
+lam 8356
+ėli 8344
+gau 8327
+rac 8301
+rėj 8293
+sme 8293
+sen 8274
+mui 8272
+sas 8272
+iza 8269
+ojų 8250
+les 8233
+a_l 8227
+aiš 8217
+ryb 8199
+esa 8186
+Å«ro 8184
+ega 8181
+kat 8166
+egi 8165
+ė_a 8149
+sla 8142
+mot 8130
+usy 8121
+eit 8115
+inį 8108
+air 8102
+tit 8093
+ole 8084
+lyv 8084
+jie 8068
+lek 8047
+suo 8046
+spo 8030
+bas 8030
+ukt 8023
+ula 8016
+Å«ti 8008
+del 8003
+enc 7995
+kšt 7982
+arė 7972
+mės 7972
+emp 7971
+los 7970
+dom 7933
+bia 7927
+van 7922
+enė 7913
+Å¡ko 7910
+run 7906
+iku 7895
+u_b 7892
+yni 7887
+sku 7881
+žsi 7880
+šių 7877
+iav 7872
+mes 7847
+lyj 7841
+pus 7826
+uva 7823
+ton 7813
+rny 7813
+sve 7811
+ašt 7803
+siū 7797
+ivi 7797
+tek 7796
+myb 7781
+alų 7767
+omp 7745
+į_a 7742
+emi 7739
+med 7732
+e_r 7726
+ė_k 7715
+škė 7710
+ont 7709
+sul 7683
+lėt 7675
+ą_d 7675
+ėse 7655
+suk 7651
+tym 7643
+eda 7620
+ire 7614
+įvy 7610
+dėt 7605
+tap 7602
+vau 7601
+sči 7598
+oms 7597
+iūl 7587
+u_i 7575
+yto 7565
+žiu 7563
+išs 7562
+org 7543
+šči 7533
+mėj 7529
+ars 7528
+Å¡iu 7516
+pel 7513
+gre 7512
+aur 7494
+ešt 7478
+izi 7458
+agr 7457
+idu 7453
+sva 7443
+ą_b 7431
+tyv 7431
+a_g 7422
+irb 7416
+e_g 7411
+sur 7410
+rba 7401
+gum 7396
+ė_n 7383
+sos 7381
+ų_į 7378
+e_l 7378
+urn 7372
+vič 7370
+nkų 7367
+ksl 7365
+ler 7364
+ėtų 7359
+u_v 7355
+syb 7347
+aki 7340
+kij 7339
+kėj 7334
+oks 7327
+lab 7291
+rys 7280
+gij 7272
+ašk 7259
+pio 7258
+ism 7250
+oka 7236
+ves 7209
+o_ž 7205
+igė 7199
+bri 7191
+iad 7190
+o_e 7180
+juo 7175
+r_m 7171
+ipa 7170
+stų 7157
+ons 7153
+klo 7148
+ovi 7126
+nut 7117
+puo 7111
+šeš 7107
+o_u 7105
+etr 7100
+vok 7097
+oju 7077
+via 7064
+imė 7056
+e_m 7052
+tyr 7050
+ete 7022
+sum 7021
+ogi 7011
+log 6992
+sud 6968
+r_j 6961
+amu 6953
+bet 6952
+rbi 6951
+pta 6947
+urt 6937
+ure 6934
+žei 6930
+tys 6930
+gus 6903
+Å¡ve 6891
+ens 6889
+ąją 6882
+žem 6863
+įmo 6858
+sar 6852
+abi 6849
+gty 6849
+inf 6844
+eži 6830
+taš 6818
+Å¡ti 6811
+aru 6808
+s_o 6785
+rtą 6773
+ą_n 6766
+uvi 6754
+ė_i 6750
+į_i 6749
+mil 6747
+odė 6745
+rėt 6727
+yba 6726
+aėj 6725
+raė 6716
+reg 6715
+dym 6713
+eln 6712
+ujo 6681
+s_y 6680
+a_m 6679
+vių 6670
+age 6668
+rep 6661
+rdu 6660
+ilo 6634
+uod 6619
+viz 6616
+sko 6610
+eka 6603
+ėmi 6584
+koj 6572
+yks 6556
+neb 6554
+ake 6552
+į_l 6545
+oci 6520
+dyb 6500
+ų_š 6478
+nst 6474
+t_p 6463
+bol 6459
+bra 6457
+lub 6451
+oro 6450
+čem 6442
+aja 6440
+doj 6440
+lyd 6430
+rol 6428
+pab 6428
+lig 6426
+bėj 6382
+a_į 6372
+amų 6369
+amb 6363
+į_t 6362
+ykl 6362
+r_l 6362
+asm 6334
+yvi 6333
+į_n 6333
+ktu 6322
+iga 6321
+anc 6317
+niz 6308
+nks 6306
+s_c 6296
+fer 6289
+pti 6277
+yko 6276
+ą_t 6271
+ser 6268
+nde 6267
+ė_d 6263
+ola 6261
+kor 6250
+ė_t 6220
+sąj 6208
+ret 6200
+lbė 6194
+tli 6188
+oku 6185
+ąju 6179
+ntų 6173
+u_m 6128
+ema 6118
+sli 6111
+ipė 6106
+ugu 6100
+mac 6082
+sig 6070
+uki 6049
+nfo 6033
+atr 6028
+iso 6025
+pap 6023
+Å¡au 6010
+u_d 5991
+r_b 5990
+iju 5987
+ogr 5984
+rob 5981
+num 5979
+paj 5978
+iru 5977
+raj 5965
+u_j 5961
+ajo 5956
+ora 5950
+tes 5948
+oda 5935
+išv 5935
+upė 5932
+vėl 5928
+soc 5926
+amą 5923
+lgi 5917
+o_f 5917
+a_r 5913
+uno 5913
+ael 5903
+rae 5898
+kiu 5895
+moj 5894
+jek 5873
+sil 5873
+ėsi 5863
+isu 5862
+ų_e 5862
+i_ž 5858
+rst 5853
+uje 5851
+įta 5848
+goj 5845
+ruk 5842
+mti 5839
+imy 5787
+ukš 5781
+sky 5777
+neg 5770
+noj 5746
+apt 5736
+dab 5732
+vij 5718
+enų 5714
+mir 5710
+iuj 5710
+uzi 5708
+nty 5706
+kyb 5693
+isk 5683
+gel 5680
+lon 5678
+mpa 5668
+e_į 5664
+ė_j 5659
+mia 5653
+l_k 5650
+apo 5643
+riv 5634
+ašy 5614
+rbu 5611
+kty 5602
+ond 5597
+enu 5595
+ope 5587
+ila 5585
+kei 5578
+tėj 5562
+lav 5552
+rbo 5547
+Å¡ie 5530
+nkė 5517
+iky 5504
+tet 5500

Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java?rev=1189246&r1=1189245&r2=1189246&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/language/LanguageIdentifierTest.java Wed Oct 26 14:40:49 2011
@@ -35,10 +35,10 @@ import org.apache.tika.io.IOUtils;
 public class LanguageIdentifierTest extends TestCase {
 
     private static final String[] languages = new String[] {
-        // TODO - currently Estonian, Greek and Lithuanian fail these tests.
+        // TODO - currently Estonian and Greek fail these tests.
         // Enable when language detection works better.
         "da", "de", /* "et", "el", */ "en", "es", "fi", "fr", "it",
-        /* "lt", */ "nl", "pt", "sv"
+        "lt", "nl", "pt", "sv"
     };
 
     public void setUp() {
@@ -52,7 +52,10 @@ public class LanguageIdentifierTest exte
             LanguageIdentifier identifier = null;
             identifier = new LanguageIdentifier(writer.getProfile());
             assertEquals(language, identifier.getLanguage());
-            assertTrue(identifier.toString(), identifier.isReasonablyCertain());
+            // Lithuanian is detected but isn't reasonably certain:
+            if (!language.equals("lt")) {
+                assertTrue(identifier.toString(), identifier.isReasonablyCertain());
+            }
         }
     }
 
@@ -99,12 +102,15 @@ public class LanguageIdentifierTest exte
         for (String language : languages) {
             for (String other : languages) {
                 if (!language.equals(other)) {
+                    if (language.equals("lt") || other.equals("lt")) {
+                        continue;
+                    }
                     ProfilingWriter writer = new ProfilingWriter();
                     writeTo(language, writer);
                     writeTo(other, writer);
                     LanguageIdentifier identifier = null;
                     identifier = new LanguageIdentifier(writer.getProfile());
-                    assertFalse(identifier.isReasonablyCertain());
+                    assertFalse("mix of " + language + " and " + other + " incorrectly detected as " + identifier, identifier.isReasonablyCertain());
                 }
             }
         }
@@ -119,7 +125,7 @@ public class LanguageIdentifierTest exte
             new LanguageIdentifier(writer.getProfile());
         assertEquals(estonian, identifier.getLanguage());
     }
-    
+
     private void writeTo(String language, Writer writer) throws IOException {
         InputStream stream =
             LanguageIdentifierTest.class.getResourceAsStream(language + ".test");